US20130058554A1 - Grid Computing on Radiology Network - Google Patents
Grid Computing on Radiology Network Download PDFInfo
- Publication number
- US20130058554A1 US20130058554A1 US13/604,954 US201213604954A US2013058554A1 US 20130058554 A1 US20130058554 A1 US 20130058554A1 US 201213604954 A US201213604954 A US 201213604954A US 2013058554 A1 US2013058554 A1 US 2013058554A1
- Authority
- US
- United States
- Prior art keywords
- medical data
- processing
- computing nodes
- subsets
- computing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 claims abstract description 134
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000003384 imaging method Methods 0.000 claims abstract description 28
- 238000002603 single-photon emission computed tomography Methods 0.000 claims description 5
- 238000002591 computed tomography Methods 0.000 claims description 4
- 238000002600 positron emission tomography Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 1
- 230000002123 temporal effect Effects 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000009206 nuclear medicine Methods 0.000 abstract description 4
- 230000001419 dependent effect Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 13
- 238000002059 diagnostic imaging Methods 0.000 description 10
- 210000000056 organ Anatomy 0.000 description 5
- 238000002604 ultrasonography Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- 239000003814 drug Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000012879 PET imaging Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000012633 nuclear imaging Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/56—Details of data transmission or power supply, e.g. use of slip rings
- A61B6/563—Details of data transmission or power supply, e.g. use of slip rings involving image data transmission via a network
Definitions
- the present invention relates generally to medical imaging and, more particularly, to a system and method of processing medical images.
- Medical imaging is one of the most useful diagnostic tools available in modern medicine. Medical imaging allows medical personnel to non-intrusively look into a living body in order to detect and assess many types of injuries, diseases, conditions, etc. Medical imaging allows doctors and technicians to more easily and correctly make a diagnosis, decide on a treatment, prescribe medication, perform surgery or other treatments, etc.
- the image may capture various details of the subject, which may include bones, organs, tissues, ducts, blood vessels, nerves, previous surgical artifacts such as implants or scar tissue, etc.
- the image or images may be two-dimensional (i.e., planar) or three-dimensional.
- the image capture may produce an image sequence or video that shows live operation, such as a functioning organ, for example.
- An imaging machine may capture an image, manipulate it, process it in some fashion in order to improve the image, display it to a doctor or technician, and store it for later use.
- Computerized image processing generally requires that the image data conform to some sort of protocol, with the protocol being a set of rules and standards that ensure that the information may be efficiently communicated and manipulated among different apparatus.
- the Digital Imaging and Communications in Medicine (DICOM) standard provides a well-defined and accepted data format and interaction protocol for communicating a processing medical image data, and is incorporated herein by reference.
- the DICOM standard is available from the Radiological Society of North America, Oak Brook, Ill. 60523-2251.
- the DICOM standard has become popular for medical imaging because it ensures that conforming machines can operate on image data communicated from other conforming machines.
- Machines that may employ the DICOM standard may be workstations, CT scanners, MR images, film digitizers, shared archives (storage devices), printers, and other devices that may be used to process and store image and patient data.
- FIG. 1 shows a conventional medical imaging system 100 .
- the medical imaging system 100 may include an imager 107 and imager controller 106 (they may be an integrated device), a patient database 110 , an output device 115 , a scanner 117 , and one or more workstations 122 .
- the imager 107 and imager controller 106 capture an image or images of a patient.
- the imager 107 may be, for example, a gamma ray camera, an X-ray imager, a magnetic resonance imager (MRI), an ultrasound imager, etc.
- the patient database 110 may store patient information (i.e., a plurality of records containing a name, vital parameters, a doctor, medical conditions, etc.), and imaging data.
- the output device 115 may be, for example, a printer, a computer monitor or other display screen, a film developer, etc.
- the scanner 117 may be a scanning device that digitizes an image.
- the workstations 122 may be used to access the patient database 110 in order to add or retrieve data. Patient information might also be stored in local databases on the processing workstations. In that case, the patient database 110 acts as a data repository for storage.
- the various components may be connected by a distributed electronic network 103 , such as, for example, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), or the Internet.
- the individual components may therefore be located in separate rooms, floors, buildings, or even separate hospitals, clinics or institutions (such as research centers that are not hospitals).
- the present invention is provided to solve the above-mentioned problem.
- a grid computing system comprises a software infrastructure, and an imaging device capable of interfacing with the software infrastructure over a distributed electronic network.
- an imaging device capable of interfacing with the software infrastructure over a distributed electronic network.
- a plurality of central processing unit (CPU) workstations capable of interfacing with the software infrastructure over the network.
- the performance of the plurality of CPUs is dependent on properly balancing load. A large dataset of medical images are split onto several processing nodes of the plurality of CPUs, respectively, such that performance and power is increased.
- a method of grid computing In the method of the present invention, a grid is limited to a nuclear medicine or radiology network. A tight and easy configuration management of computing nodes, and a tight load balancing between standardized nodes are provided. An existing network of central processing units (CPUs) is utilized, such that the greatest benefit is provided at the lowest cost.
- CPUs central processing units
- FIG. 1 is a conventional medical imaging system
- FIG. 2 shows the grid computing system according to an exemplary embodiment of the present invention
- FIG. 3 is a flow chart of the method of grid computing according to an exemplary embodiment of the present invention.
- FIGS. 4A and 4B show examples of a gird computing system in which the number of computing nodes increases
- FIG. 5 shows a block diagram showing an example of processes of the grid computing system
- FIG. 6 shows an example of a series of steps of processes of the grid computing system
- FIG. 7 shows an example of a grid computing system with four computing nodes
- FIG. 8 shows a block diagram of modules and components according to another embodiment of the present invention.
- a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
- a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
- an application running on a server and the server can be a component.
- One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.
- Embodiments of the present invention include the methods described and may be implemented using one or more apparatus, such as processing apparatus coupled to electronic media.
- Embodiments of the present invention may be stored on an electronic media (electronic memory, RAM, ROM, EEPROM) or programmed as computer code (e.g., source code, object code or any suitable programming language) to be executed by one or more processors operating in conjunction with one or more electronic storage media.
- This electronic storage media may include, for example a non-transitory electronic storage medium/media such as a register, or other electronic repository or electronic storage location for data that is capable of storing data represented in electronic form, such as bits, bytes, kilobytes, waveforms, electronic signals, digital format and other data types, formats and forms of data.
- a non-transitory electronic storage medium/media such as a register, or other electronic repository or electronic storage location for data that is capable of storing data represented in electronic form, such as bits, bytes, kilobytes, waveforms, electronic signals, digital format and other data types, formats and forms of data.
- Embodiments of the present invention may be implemented using one or more processing devices, or processing modules.
- the processing devices, or modules may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices and shared or transmitted between a plurality of processing devices.
- the grid computing system 20 comprises a master processing workstation 202 , an imaging device 204 , and a plurality of computing nodes 206 1 - 206 n .
- each workstation is/can be both master and computing node.
- the imaging device 204 and the plurality of computing nodes 206 1 - 206 n interface with the master processing workstation 202 over a network such as, for example, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), the Internet, or the like.
- LAN local area network
- WAN wide area network
- VPN virtual private network
- the master processing workstation 202 may be based on the universally accepted Windows NT S operating system with a graphical user interface (GUI) that is simple and intuitive.
- GUI graphical user interface
- the invention is not restricted to any particular operating system or platform, but works on any platform or operation system.
- the imaging device 204 may be a combined scanning device, such as, for example, positron emission tomography/computed tomography (PET-CT), single photon emission computed tomography/computed tomography (SPECT-CT), or the like. It will be appreciated by those skilled in the art that the imaging device 204 also can be a single imaging device such as, for example, SPECT, planar imaging, or PET or MRI or Ultrasound or any other type of data collecting device.
- PET-CT positron emission tomography/computed tomography
- SPECT-CT single photon emission computed tomography/computed tomography
- the imaging device 204 also can be a single imaging device such as, for example, SPECT, planar imaging, or PET or MRI or Ultrasound or any other type of data collecting device.
- the plurality of computing nodes 206 1 - 206 n can be clusters and networks of workstations interfacing with the master processing workstation 202 over the network, clusters and networks of personal computers interfacing with the master processing workstation 202 over the network, or a combination of clusters and networks of workstations and of personal computers interfacing with the master processing workstation 202 over the network. Accordingly, multimodality images can be viewed on the computing nodes 206 1 - 206 n , alongside CT, MR, ultrasound, NM, angiography images, or the like.
- the computing nodes 206 1 - 206 n allow access to a universe of information and provide unlimited functionality.
- Performance of the plurality of computing nodes 206 1 - 206 n is dependent on the ability to balance load, and maintain parallel processing software infrastructure (e.g., versions, updates, software, hardware obsolescence, etc.).
- parallel processing software infrastructure e.g., versions, updates, software, hardware obsolescence, etc.
- a large medical dataset is split onto several processing nodes.
- the acceleration ratios obtained are usually equal to the number of computing nodes.
- the medical dataset is not limited to images.
- list mode processing in nuclear medicine carries out processing on count data in the form of a sequential list of numerical values.
- FIG. 3 is a flow chart of a method of grid computing according to an exemplary embodiment of the present invention.
- a network grid is limited to a nuclear medicine or radiology network. This has the beneficial effect of reserving the computing power for those applications that require the most intensive processing.
- step S 303 a tight and easy configuration management of computing nodes is provided, and a tight load balancing between standardized nodes is also provided (step S 305 ).
- An existing network of central processing units (CPUs) is utilized in step S 307 , such that the greatest benefit is provided at the lowest cost (eq., cycles on idle machines are not wasted).
- the grid computing system and method as described herein provide several benefits such as increased performance and power (e.g., maximum performance and reliability).
- FIGS. 4A and 4B another embodiment of the present invention will be described.
- the grid computing system 40 a comprises a master processing workstation 402 , an imaging device 404 , and a plurality of computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( m ) (where “m” is any suitable number).
- the master processing workstation 402 parses the medical image data into m subsets of image data, and transmits these m subsets of image data to the associated m computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( m ), respectively.
- subsets of processed data are transmitted back to the master processing workstation 402 , at which the subsets of processed data are combined to generate three-dimensional medical image data representation.
- the detailed processing of the grid system will be described in relation to FIG. 5 .
- system 40 b when the grid computing system is updated by increasing the number of the computing nodes from m to n, besides the master processing workstation 402 , the imaging device 404 , and the plurality of computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( m ), the updated grid computing system 40 b further comprises a plurality of newly added computing nodes 406 (m+1), 406 (m+2) . . . 406 ( n ) (where “n” is any suitable number no less than “m”).
- the master processing workstation 402 adapts itself to the new number “n” without reconfiguration, i.e., the master processing workstation 402 parses the medical image data into n subsets of split image data, and transmits these m subset of split image data to the associated n computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( n ), respectively.
- the master processing workstation 402 parses the medical image data into n subsets of split image data, and transmits these m subset of split image data to the associated n computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( n ), respectively.
- new workstations for example, a new laboratory, nurses' station, reading room which has a particular number of computing nodes is added in the hospital, the overall performance of each processing may be increased, assuming that not all computers will be available at a particular time.
- the number of potential processing modules for the grid system increase.
- the grid computing system 40 a or 40 b shown in FIGS. 4A and 4B when parts of the network, such as a particular number of the computing nodes, become unavailable for processing data (for example power outage), as long as there is still one node that is operational, the entire grid computing system will continue performing the data processing without termination, or interruption. Therefore, in accordance with the present invention, the grid computing system 40 a or 40 b approach is more resilient and adaptive than the conventionally used centralized approach.
- the grid computing system 40 a or 40 b is adapted for use with a centralized processing server and serve “ready made” images to thin clients (client modules that do not perform any processing functions or operations).
- cloud computing in which the cloud is typically a rented computing utility, in the present invention it is the hospital's own network of workstations, processing devices and personal computers (PCs) (i.e., the user may define the hospital's workstations and PCs as the computing nodes of the grid computing system).
- PCs personal computers
- FIG. 5 illustrates a diagram 500 showing an example of processes of the grid computing system according to an embodiment of the present invention.
- medical image data 502 is captured by image device 404 , and transmitted to master processing work station 402 , where the medical image data 502 is parsed into data splices, or subsets 504 ( 1 ), 504 ( 2 ) . . . 504 ( n ). These data splices, or subsets 504 ( 1 ), 504 ( 2 ) . . . 504 ( n ) are transmitted to associated computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( n ), (where “n” is any suitable number), respectively.
- data splice, or subset 504 ( 1 ) is transmitted to computing node 406 ( 1 )
- data splice, or subset 504 ( 2 ) is transmitted to computing node 406 ( 2 ) . . .
- data splice, or subset 504 ( n ) is transmitted to computing node 406 ( n ).
- the processed data subsets 506 ( 1 ), 506 ( 2 ) . . . 506 ( n ) are output from the associated computing nodes 406 ( 1 ), 406 ( 2 ) . . . 406 ( n ), respectively, and transmitted back to master processing work station 402 .
- the predetermined image data processing includes processing the subset data to generate a three-dimensional (3-D) representation.
- the image processing may be any desired processing operations provided as instructions to the processing module.
- the processed data subsets 506 ( 1 ), 506 ( 2 ) . . . 506 ( n ) are combined according to their initial sequence to generate three dimensional data representation 508 , which is output from the master processing workstation 402 .
- FIG. 6 illustrates an example of a series of steps of processes of the grid computing system according to an embodiment of the present invention.
- the series of steps 600 may be stored on a non-transitory computer readable medium or media (e.g., RAM, ROM, EEPRPOM, DRAM or other memory, electronic storage device or registry) and may be executed by a processor or plurality of processors.
- the steps 600 may be computer code or other program code (e.g., source code) that may be compiled into object code.
- the code, stored on a medium and/or accessed, is a module, which may include electronic storage and/or processing functionality.
- the storage medium may be resident on the device (local) or accessed from a remote device (remote).
- the steps 600 are typically executed by a processor having adequate speed and processing capabilities. The execution may be at the client device and/or an associated server device.
- the steps 600 may be computer code or other program code (e.g., source code) that may be compiled into object code.
- the code, stored on a medium and/or accessed, is a module.
- the steps 600 may be stored on any one or more suitable modules described in relation to FIGS. 4A , 4 B, 5 , 7 and 8 herein.
- FIG. 6 shows that program code 600 begins with start step 602 .
- a particular number of CPUs for example n CPUs, are defined as “n” (where “n” is any suitable number) computing nodes of the grid computing system by the user.
- an imaging device e.g., See FIG. 4 , element 404
- the master processing workstation e.g., See FIG. 4 , element 402
- step 610 a determination is made whether the number of the computing nodes changes. If not, “no” line 611 leads to step 614 . If more computing nodes are available to the grid computing system (i.e., the number of available processing nodes increases), or if some computing nodes in the system become unavailable (i.e., the number decreases), “yes” line 609 leads to step 612 , in which the number of computing nodes is updated, and then in step 614 the captured image data is parsed into data subsets according to the number of available computing nodes. For example, if the number of the available computing nodes is “n”, the captured image data may be parsed into n subsets of data, which are data subsets (e.g., See FIG. 5 , elements 506 ( 1 ), 506 ( 2 ) . . . 506 ( n )).
- the data subsets which are desired to be processed may be selected and transmitted to the associated one or more available computing nodes. For example, among the n subsets of data, if the user only needs data subset (e.g., See FIG. 5 , element 506 ( 5 )) to be processed, only three data subsets, including (i) the desired data subset (e.g., See FIG. 5 , element 506 ( 5 )), (ii) data subset (e.g., See FIG. 5 , element 506 ( 4 )) which is the data subset prior to the desired data subset (e.g., See FIG.
- step 620 at each computing node, the data subset is processed according to the predetermined data processing, which may include manipulations, or execution of program code, and in step 622 the processed data subsets are transmitted from the computing nodes (e.g., See FIG. 4 , element 406 ( 1 ), 406 ( 2 ) . . . 406 ( n )), respectively, to the master processing workstation (e.g., See FIG. 4 , element 402 ).
- the computing nodes e.g., See FIG. 4 , element 406 ( 1 ), 406 ( 2 ) . . . 406 ( n )
- the master processing workstation e.g., See FIG. 4 , element 402 .
- step 624 the processed data subsets and those data subsets not selected in step 616 (if any) may be combined based on the time sequence of the data subsets to generate three-dimensional medical data representation (e.g., See FIG. 5 , element 508 ).
- the generated three-dimensional (3-D) data representation (e.g., See FIG. 5 , element 508 ) may be output from the master processing workstation (e.g., See FIG. 4 , element 402 ), as shown in step 626 .
- step 628 a determination is made whether there is more captured image data to be processed. If so, “yes” line 627 leads back to step 608 . Otherwise, if there is no more captured image data, “no” line 627 leads to end step 630 .
- the captured medical data may be parsed into any number of subsets, instead of the same number equal to the number of the computing nodes.
- the whole captured medical data set may be transmitted to each of the computing node without being parsed.
- one-third (1 ⁇ 3) of the whole medical data set may be transmitted to the first computing node, and the remaining portion (two-thirds) of the whole medical data set may be transmitted to the second computing node, so that there will be no data transmitted to the third computing node.
- the master processing workstation (see FIG. 4 , element 402 ) may get feedback information indicating the data processing rate of the computing node from each computing node, respectively. Based on the data processing rate of each computing node, the master processing workstation may assign different amount of medical data to these computing nodes.
- FIG. 7 shows an example of a grid computing system with four computing nodes.
- the computing system shown in FIG. 7 may be implemented using one or more processing devices, or processing modules or facilities.
- the processing devices, or modules, or facilities may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices and shared or transmitted between a plurality of processing devices.
- the master processing workstation 702 may assign one-half of the whole medical data set to the first computing node 706 ( 1 ), and assign one-fourth of the whole medical data set to the second computing node 706 ( 2 ) and the third computing node 706 ( 3 ), respectively.
- Another example is that if data processing rate of a particular computing code is much lower than other computing nodes, the master processing workstation may stop transmitting data to this particular computing node, and adjust the number of the subsets of data to be transmitted to other computing nodes. Therefore, the data processing rate of the whole system may increase.
- the master processing workstation and the computing nodes may be any device with a processor that might be connected to the computing system, for example, personal computer, cell phone, PDA, television, video game device and the like.
- the original captured medical data may be not only two dimensional image data obtained by any image obtaining unit, but also one dimensional ultrasound data.
- the grid computing system adapts itself to the number of the computing nodes, so the medical image data may be processed more efficiently.
- the medical image data is obtained by the imaging device (e.g., See FIG. 4 , element 404 ) at a predetermined frequency
- the three dimensional data representation may be generated to show a dynamic operation of a functioning organ of a living body.
- the three dimensional data representation of the dynamic operation of the functioning organ is generated at regular intervals, such as every month or every year, the operation of the functioning organ may be monitored and stored for the hospital's record.
- FIG. 8 shows a block diagram 800 of modules and components according to another embodiment of the present invention.
- Embodiments FIG. 8 may be implemented using one or more processing devices, or processing modules, or facilities.
- the processing devices, or modules, or facilities may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices, modules or facilities and shared or transmitted between a plurality of processing devices.
- FIG. 8 includes medical image data, a defining unit 802 , a determining unit 804 , a parsing unit 806 , processing nodes 807 ( a ) . . . ( n ) (where “n” is any suitable number), processing unit 808 , transmitting unit 810 , generating unit 812 , output unit 814 and memory unit 816 .
- the data which is typically medical image data that is in a particular format, such as pixels, two-dimensional, one-dimensional or other data obtained from an imaging process of a patient.
- the image data is accessed by defining unit 802 .
- the defining unit 802 defines a plurality of computing nodes that are available to perform processing operations, manipulations and/or functions.
- the defined computing nodes may be defined, or identified by a user, or program code by sending an API (Application Program Interface), or “ping” to possible computing nodes as a status check to determine all possible computing nodes that may be available to perform processing operations.
- API Application Program Interface
- the determination unit 804 is used to determine which of the plurality of computing nodes is available for performing processing. Since all possible nodes that are identified by the defining unit may not be available to actually perform proceeding functionality, the determining unit 804 can select those nodes that respond to the API or ping, as actually receptive to processing requests.
- the parsing unit 806 is used for parsing the medical data into a plurality of medical data subsets.
- the number of the medical data subsets being based on the number of the available computing nodes, or processing nodes, 807 ( a ) . . . ( n ).
- the number of subsets may be a function of the nodes (generally 807 ) processing power, or capability, or speed. Indeed one embodiment of the present invention is that the number of subsets is equal to the number of processing nodes 807 .
- each of the processing nodes 807 may receive a disproportionate amount of subsets based on the processing capability of each node 807 .
- some node 807 that are available may not receive any subsets, while other ones of the nodes 807 may receive a plurality of subsets.
- the processing unit 808 is used for processing, organizing, compiling and/or re-assembling each subset received from an associated one of the plurality of computing nodes 807 .
- processing unit 808 may perform actual processing functionality of one or more subsets of data itself.
- This processing unit 808 is typically used as a managing, or control processing unit, to control the final processing of the processed data received from nodes 807 .
- the transmitting unit 810 is used to transmit the processed medical data subsets to a master node, which may be processing unit 808 , or other node.
- the generating unit 812 is used for generating a representation of the image data at the master node by combining the processed medical data subsets.
- the representation may be, for example, a three-dimensional (3D) representation, a voxel representation, a color representation or model of the image data.
- the output unit 814 is used to output the representation, This unit 814 may be a computer screen, printer or other suitable output device to display or output the representation.
- the memory 816 is also available to store the representation output from output module 816 .
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
- This application is a Continuation-In-Part of U.S. Ser. No. 10/880,112, filed Jun. 29, 2004, now U.S. Pat. No. ______, the entirety of which is hereby incorporated by reference herein.
- 1. Field of the Invention
- The present invention relates generally to medical imaging and, more particularly, to a system and method of processing medical images.
- 2. Description of the Background Art
- Medical imaging is one of the most useful diagnostic tools available in modern medicine. Medical imaging allows medical personnel to non-intrusively look into a living body in order to detect and assess many types of injuries, diseases, conditions, etc. Medical imaging allows doctors and technicians to more easily and correctly make a diagnosis, decide on a treatment, prescribe medication, perform surgery or other treatments, etc.
- There are medical imaging processes of many types and for many different purposes, situations, or uses. They commonly share the ability to create an image of a bodily region of a patient, and can do so non-invasively. Examples of some common medical imaging types are nuclear imaging, magnetic resonance imaging (MRI), ultrasound, X-rays, tomography of various types, etc. Using these or other imaging types and associated machines, an image or series of images may be captured. Other devices may then be used to process the image in some fashion. Finally, a doctor or technician may read the image in order to provide a diagnosis.
- The image may capture various details of the subject, which may include bones, organs, tissues, ducts, blood vessels, nerves, previous surgical artifacts such as implants or scar tissue, etc. The image or images may be two-dimensional (i.e., planar) or three-dimensional. In addition, the image capture may produce an image sequence or video that shows live operation, such as a functioning organ, for example. An imaging machine may capture an image, manipulate it, process it in some fashion in order to improve the image, display it to a doctor or technician, and store it for later use.
- Computerized image processing generally requires that the image data conform to some sort of protocol, with the protocol being a set of rules and standards that ensure that the information may be efficiently communicated and manipulated among different apparatus. The Digital Imaging and Communications in Medicine (DICOM) standard provides a well-defined and accepted data format and interaction protocol for communicating a processing medical image data, and is incorporated herein by reference. The DICOM standard is available from the Radiological Society of North America, Oak Brook, Ill. 60523-2251.
- The DICOM standard has become popular for medical imaging because it ensures that conforming machines can operate on image data communicated from other conforming machines. Machines that may employ the DICOM standard may be workstations, CT scanners, MR images, film digitizers, shared archives (storage devices), printers, and other devices that may be used to process and store image and patient data.
-
FIG. 1 shows a conventionalmedical imaging system 100. Themedical imaging system 100 may include animager 107 and imager controller 106 (they may be an integrated device), apatient database 110, anoutput device 115, ascanner 117, and one ormore workstations 122. Theimager 107 andimager controller 106 capture an image or images of a patient. Theimager 107 may be, for example, a gamma ray camera, an X-ray imager, a magnetic resonance imager (MRI), an ultrasound imager, etc. Thepatient database 110 may store patient information (i.e., a plurality of records containing a name, vital parameters, a doctor, medical conditions, etc.), and imaging data. Theoutput device 115 may be, for example, a printer, a computer monitor or other display screen, a film developer, etc. Thescanner 117 may be a scanning device that digitizes an image. Theworkstations 122 may be used to access thepatient database 110 in order to add or retrieve data. Patient information might also be stored in local databases on the processing workstations. In that case, thepatient database 110 acts as a data repository for storage. The various components may be connected by a distributedelectronic network 103, such as, for example, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), or the Internet. The individual components may therefore be located in separate rooms, floors, buildings, or even separate hospitals, clinics or institutions (such as research centers that are not hospitals). - Computerized image processing is well known in the art. However, the need for computing power is ever increasing. For example, recent developments in tomographic reconstruction processes require more and more computing power to more accurately model the physics of image formation. Current processing software memory and processing power requirements may already exceed the specifications of the most powerful computers currently available on the market. As an example, in the field of SPECT imaging, the OSEM 3D reconstruction algorithm currently requires several hours of processing time to process a 256-cube volume, and is therefore not usable in a clinical practice. The processing power requirement is projected to only increase as scanners produce more and more data as resolution and speed increase, and as interest grows in obtaining full resolution co-registered or fused images from different modalities, such as SPECT-CT, PET-CT, SPECT-MRI, etc. Accordingly, there exists a present need in the art to reduce overall radiological image processing time.
- The present invention is provided to solve the above-mentioned problem. According to an aspect of the present invention, there is provided a grid computing system. The grid computing system comprises a software infrastructure, and an imaging device capable of interfacing with the software infrastructure over a distributed electronic network. Also included is a plurality of central processing unit (CPU) workstations capable of interfacing with the software infrastructure over the network. The performance of the plurality of CPUs is dependent on properly balancing load. A large dataset of medical images are split onto several processing nodes of the plurality of CPUs, respectively, such that performance and power is increased.
- According to another aspect of the present invention, there is provided a method of grid computing. In the method of the present invention, a grid is limited to a nuclear medicine or radiology network. A tight and easy configuration management of computing nodes, and a tight load balancing between standardized nodes are provided. An existing network of central processing units (CPUs) is utilized, such that the greatest benefit is provided at the lowest cost.
- The accompanying drawings, which are incorporated herein and form part of the specification, illustrate various embodiments of the present invention and, together with the description, further serve to explain the principles of the invention and to enable a person skilled in the pertinent art to make and use the invention. In the drawings, like reference numbers indicate identical or functionally similar elements. A more complete appreciation of the invention and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:
-
FIG. 1 is a conventional medical imaging system; -
FIG. 2 shows the grid computing system according to an exemplary embodiment of the present invention; -
FIG. 3 is a flow chart of the method of grid computing according to an exemplary embodiment of the present invention; -
FIGS. 4A and 4B show examples of a gird computing system in which the number of computing nodes increases; -
FIG. 5 shows a block diagram showing an example of processes of the grid computing system; -
FIG. 6 shows an example of a series of steps of processes of the grid computing system; -
FIG. 7 shows an example of a grid computing system with four computing nodes; and -
FIG. 8 shows a block diagram of modules and components according to another embodiment of the present invention. - It is noted that in this disclosure and particularly in the claims and/or paragraphs, terms such as “comprises,” “comprised,” “comprising,” and the like can have the meaning attributed to it in U.S. patent law; that is, they can mean “includes,” “included,” “including,” “including, but not limited to” and the like, and allow for elements not explicitly recited. Terms such as “consisting essentially of” and “consists essentially of” have the meaning ascribed to them in U.S. patent law; that is, they allow for elements not explicitly recited, but exclude elements that are found in the prior art or that affect a basic or novel characteristic of the invention. These and other embodiments are disclosed or are apparent from and encompassed by, the following description. As used in this application, the terms “component” and “system” are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a server and the server can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.
- Furthermore, the detailed description describes various embodiments of the present invention for illustration purposes and embodiments of the present invention include the methods described and may be implemented using one or more apparatus, such as processing apparatus coupled to electronic media. Embodiments of the present invention may be stored on an electronic media (electronic memory, RAM, ROM, EEPROM) or programmed as computer code (e.g., source code, object code or any suitable programming language) to be executed by one or more processors operating in conjunction with one or more electronic storage media. This electronic storage media may include, for example a non-transitory electronic storage medium/media such as a register, or other electronic repository or electronic storage location for data that is capable of storing data represented in electronic form, such as bits, bytes, kilobytes, waveforms, electronic signals, digital format and other data types, formats and forms of data.
- Embodiments of the present invention may be implemented using one or more processing devices, or processing modules. The processing devices, or modules, may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices and shared or transmitted between a plurality of processing devices.
- As illustrated in
FIG. 2 , thegrid computing system 20 comprises amaster processing workstation 202, animaging device 204, and a plurality of computing nodes 206 1-206 n. In accordance with the principle of a computing “grid,” each workstation is/can be both master and computing node. Theimaging device 204 and the plurality of computing nodes 206 1-206 n, interface with themaster processing workstation 202 over a network such as, for example, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), the Internet, or the like. - According to one particular example embodiment of the invention, the
master processing workstation 202 may be based on the universally accepted Windows NTS operating system with a graphical user interface (GUI) that is simple and intuitive. However, the invention is not restricted to any particular operating system or platform, but works on any platform or operation system. - Referring to
FIG. 2 , theimaging device 204 may be a combined scanning device, such as, for example, positron emission tomography/computed tomography (PET-CT), single photon emission computed tomography/computed tomography (SPECT-CT), or the like. It will be appreciated by those skilled in the art that theimaging device 204 also can be a single imaging device such as, for example, SPECT, planar imaging, or PET or MRI or Ultrasound or any other type of data collecting device. - The plurality of computing nodes 206 1-206 n, can be clusters and networks of workstations interfacing with the
master processing workstation 202 over the network, clusters and networks of personal computers interfacing with themaster processing workstation 202 over the network, or a combination of clusters and networks of workstations and of personal computers interfacing with themaster processing workstation 202 over the network. Accordingly, multimodality images can be viewed on the computing nodes 206 1-206 n, alongside CT, MR, ultrasound, NM, angiography images, or the like. The computing nodes 206 1-206 n, allow access to a universe of information and provide unlimited functionality. - Performance of the plurality of computing nodes 206 1-206 n, is dependent on the ability to balance load, and maintain parallel processing software infrastructure (e.g., versions, updates, software, hardware obsolescence, etc.). In the parallel processing method of the present invention, a large medical dataset is split onto several processing nodes. The acceleration ratios obtained are usually equal to the number of computing nodes.
- It is noted that the medical dataset is not limited to images. The benefit of more computing power allows one to consider processing raw information from the scanner before it is actually formatted into images, for example, list mode processing in nuclear medicine carries out processing on count data in the form of a sequential list of numerical values.
- When demand processing is performed on the cluster of processing nodes 206 1-206 n, significant and sustainable computer power improvement is achieved (e.g., maximum performance and reliability). Alternatively, when reconstruction load is spread on clusters and networks of workstations and personal computers 206 1-206 n, good performance is achieved. Users such as research sites can mix the workstations and personal computers 206 1-206 n to achieve the highest demand of computing power.
-
FIG. 3 is a flow chart of a method of grid computing according to an exemplary embodiment of the present invention. In step S301, a network grid is limited to a nuclear medicine or radiology network. This has the beneficial effect of reserving the computing power for those applications that require the most intensive processing. In step S303, a tight and easy configuration management of computing nodes is provided, and a tight load balancing between standardized nodes is also provided (step S305). An existing network of central processing units (CPUs) is utilized in step S307, such that the greatest benefit is provided at the lowest cost (eq., cycles on idle machines are not wasted). - The grid computing system and method as described herein provide several benefits such as increased performance and power (e.g., maximum performance and reliability).
- Next, referring to
FIGS. 4A and 4B , another embodiment of the present invention will be described. - As illustrated in
FIG. 4A , the grid computing system 40 a comprises amaster processing workstation 402, animaging device 404, and a plurality of computing nodes 406(1), 406(2) . . . 406(m) (where “m” is any suitable number). After the medical image is captured by theimaging device 404, themaster processing workstation 402 parses the medical image data into m subsets of image data, and transmits these m subsets of image data to the associated m computing nodes 406(1), 406(2) . . . 406(m), respectively. After data processing at each computing node 406(1), 406(2) . . . 406(m), subsets of processed data are transmitted back to themaster processing workstation 402, at which the subsets of processed data are combined to generate three-dimensional medical image data representation. The detailed processing of the grid system will be described in relation toFIG. 5 . - As illustrated in
FIG. 4B , system 40 b, when the grid computing system is updated by increasing the number of the computing nodes from m to n, besides themaster processing workstation 402, theimaging device 404, and the plurality of computing nodes 406(1), 406(2) . . . 406(m), the updated grid computing system 40 b further comprises a plurality of newly added computing nodes 406(m+1), 406(m+2) . . . 406(n) (where “n” is any suitable number no less than “m”). After the number of the computing nodes increases from “m” to “n”, themaster processing workstation 402 adapts itself to the new number “n” without reconfiguration, i.e., themaster processing workstation 402 parses the medical image data into n subsets of split image data, and transmits these m subset of split image data to the associated n computing nodes 406(1), 406(2) . . . 406(n), respectively. In this case, when new workstations are added, for example, a new laboratory, nurses' station, reading room which has a particular number of computing nodes is added in the hospital, the overall performance of each processing may be increased, assuming that not all computers will be available at a particular time. Thus, as the number of processing computers grows, or increases, the number of potential processing modules for the grid system increase. - Furthermore, it is an embodiment of the present invention that in the grid computing system 40 a or 40 b shown in
FIGS. 4A and 4B , when parts of the network, such as a particular number of the computing nodes, become unavailable for processing data (for example power outage), as long as there is still one node that is operational, the entire grid computing system will continue performing the data processing without termination, or interruption. Therefore, in accordance with the present invention, the grid computing system 40 a or 40 b approach is more resilient and adaptive than the conventionally used centralized approach. - In accordance with the present invention, the grid computing system 40 a or 40 b is adapted for use with a centralized processing server and serve “ready made” images to thin clients (client modules that do not perform any processing functions or operations). Thus, when compared with cloud computing, in which the cloud is typically a rented computing utility, in the present invention it is the hospital's own network of workstations, processing devices and personal computers (PCs) (i.e., the user may define the hospital's workstations and PCs as the computing nodes of the grid computing system).
-
FIG. 5 illustrates a diagram 500 showing an example of processes of the grid computing system according to an embodiment of the present invention. - As shown in
FIG. 5 ,medical image data 502 is captured byimage device 404, and transmitted to masterprocessing work station 402, where themedical image data 502 is parsed into data splices, or subsets 504(1), 504(2) . . . 504(n). These data splices, or subsets 504(1), 504(2) . . . 504(n) are transmitted to associated computing nodes 406(1), 406(2) . . . 406(n), (where “n” is any suitable number), respectively. For example, data splice, or subset 504(1) is transmitted to computing node 406(1), data splice, or subset 504(2) is transmitted to computing node 406(2) . . . and data splice, or subset 504(n) is transmitted to computing node 406(n). At each computing node, after predetermined image data processing, manipulation or operation is performed, the processed data subsets 506(1), 506(2) . . . 506(n) are output from the associated computing nodes 406(1), 406(2) . . . 406(n), respectively, and transmitted back to masterprocessing work station 402. The predetermined image data processing includes processing the subset data to generate a three-dimensional (3-D) representation. The image processing may be any desired processing operations provided as instructions to the processing module. - At the master
processing work station 402, the processed data subsets 506(1), 506(2) . . . 506(n) are combined according to their initial sequence to generate threedimensional data representation 508, which is output from themaster processing workstation 402. -
FIG. 6 illustrates an example of a series of steps of processes of the grid computing system according to an embodiment of the present invention. The series ofsteps 600 may be stored on a non-transitory computer readable medium or media (e.g., RAM, ROM, EEPRPOM, DRAM or other memory, electronic storage device or registry) and may be executed by a processor or plurality of processors. Thesteps 600 may be computer code or other program code (e.g., source code) that may be compiled into object code. The code, stored on a medium and/or accessed, is a module, which may include electronic storage and/or processing functionality. The storage medium may be resident on the device (local) or accessed from a remote device (remote). Thesteps 600 are typically executed by a processor having adequate speed and processing capabilities. The execution may be at the client device and/or an associated server device. Thesteps 600 may be computer code or other program code (e.g., source code) that may be compiled into object code. The code, stored on a medium and/or accessed, is a module. Thesteps 600 may be stored on any one or more suitable modules described in relation toFIGS. 4A , 4B, 5, 7 and 8 herein. - Specifically,
FIG. 6 shows thatprogram code 600 begins withstart step 602. In step 604 a particular number of CPUs, for example n CPUs, are defined as “n” (where “n” is any suitable number) computing nodes of the grid computing system by the user. Instep 606, an imaging device (e.g., SeeFIG. 4 , element 404) captures medical image data and the captured image data is transmitted to the master processing workstation (e.g., SeeFIG. 4 , element 402), as shown instep 608. - In step 610 a determination is made whether the number of the computing nodes changes. If not, “no”
line 611 leads to step 614. If more computing nodes are available to the grid computing system (i.e., the number of available processing nodes increases), or if some computing nodes in the system become unavailable (i.e., the number decreases), “yes”line 609 leads to step 612, in which the number of computing nodes is updated, and then instep 614 the captured image data is parsed into data subsets according to the number of available computing nodes. For example, if the number of the available computing nodes is “n”, the captured image data may be parsed into n subsets of data, which are data subsets (e.g., SeeFIG. 5 , elements 506(1), 506(2) . . . 506(n)). - In
step 616, the data subsets which are desired to be processed may be selected and transmitted to the associated one or more available computing nodes. For example, among the n subsets of data, if the user only needs data subset (e.g., SeeFIG. 5 , element 506(5)) to be processed, only three data subsets, including (i) the desired data subset (e.g., SeeFIG. 5 , element 506(5)), (ii) data subset (e.g., SeeFIG. 5 , element 506(4)) which is the data subset prior to the desired data subset (e.g., SeeFIG. 5 , element 506(5)) in time sequence, and (iii) data subset (e.g., SeeFIG. 5 , element 506(6)) which is the data subset following the desired data subset (e.g., SeeFIG. 5 , element 506(5)) in time sequence, are required to be transmitted to the computing nodes, and other data subsets may not be transmitted. In this way, the grid computing system works more efficiently without transmitting unnecessary data. - In
step 620, at each computing node, the data subset is processed according to the predetermined data processing, which may include manipulations, or execution of program code, and instep 622 the processed data subsets are transmitted from the computing nodes (e.g., SeeFIG. 4 , element 406(1), 406(2) . . . 406(n)), respectively, to the master processing workstation (e.g., SeeFIG. 4 , element 402). - In
step 624, the processed data subsets and those data subsets not selected in step 616 (if any) may be combined based on the time sequence of the data subsets to generate three-dimensional medical data representation (e.g., SeeFIG. 5 , element 508). The generated three-dimensional (3-D) data representation (e.g., SeeFIG. 5 , element 508) may be output from the master processing workstation (e.g., SeeFIG. 4 , element 402), as shown instep 626. - In step 628 a determination is made whether there is more captured image data to be processed. If so, “yes”
line 627 leads back tostep 608. Otherwise, if there is no more captured image data, “no”line 627 leads to endstep 630. - In accordance with the present invention, alternatively, in
step 614, the captured medical data may be parsed into any number of subsets, instead of the same number equal to the number of the computing nodes. For example, the whole captured medical data set may be transmitted to each of the computing node without being parsed. Another example, for a computing system with three computing nodes, under the control of the master processing workstation, one-third (⅓) of the whole medical data set may be transmitted to the first computing node, and the remaining portion (two-thirds) of the whole medical data set may be transmitted to the second computing node, so that there will be no data transmitted to the third computing node. - In accordance with the present invention, at each computing node, based on the different data processing capacity at each computing node, the subset of medical data may be processed at different data processing rate. Therefore, the master processing workstation (see
FIG. 4 , element 402) may get feedback information indicating the data processing rate of the computing node from each computing node, respectively. Based on the data processing rate of each computing node, the master processing workstation may assign different amount of medical data to these computing nodes. -
FIG. 7 shows an example of a grid computing system with four computing nodes. The computing system shown inFIG. 7 may be implemented using one or more processing devices, or processing modules or facilities. The processing devices, or modules, or facilities, may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices and shared or transmitted between a plurality of processing devices. - For example, as shown in
FIG. 7 , if the data processing rate, or capacity, of a first computing node 706(1) is twice that of the data processing rate, or capacity, of the second computing node 706(2) and the third computing node 706(3), themaster processing workstation 702 may assign one-half of the whole medical data set to the first computing node 706(1), and assign one-fourth of the whole medical data set to the second computing node 706(2) and the third computing node 706(3), respectively. Another example is that if data processing rate of a particular computing code is much lower than other computing nodes, the master processing workstation may stop transmitting data to this particular computing node, and adjust the number of the subsets of data to be transmitted to other computing nodes. Therefore, the data processing rate of the whole system may increase. - In accordance with the present invention, the master processing workstation and the computing nodes, may be any device with a processor that might be connected to the computing system, for example, personal computer, cell phone, PDA, television, video game device and the like.
- In accordance with the present invention, the original captured medical data may be not only two dimensional image data obtained by any image obtaining unit, but also one dimensional ultrasound data.
- Furthermore, in accordance with the present invention, the grid computing system adapts itself to the number of the computing nodes, so the medical image data may be processed more efficiently. For example, when the medical image data is obtained by the imaging device (e.g., See
FIG. 4 , element 404) at a predetermined frequency, the three dimensional data representation may be generated to show a dynamic operation of a functioning organ of a living body. Moreover, if the three dimensional data representation of the dynamic operation of the functioning organ is generated at regular intervals, such as every month or every year, the operation of the functioning organ may be monitored and stored for the hospital's record. -
FIG. 8 shows a block diagram 800 of modules and components according to another embodiment of the present invention. EmbodimentsFIG. 8 may be implemented using one or more processing devices, or processing modules, or facilities. The processing devices, or modules, or facilities, may be coupled such that portions of the processing and/or data manipulation may be performed at one or more processing devices, modules or facilities and shared or transmitted between a plurality of processing devices.FIG. 8 includes medical image data, a definingunit 802, a determiningunit 804, aparsing unit 806, processing nodes 807(a) . . . (n) (where “n” is any suitable number),processing unit 808, transmittingunit 810, generatingunit 812,output unit 814 andmemory unit 816. - The data, which is typically medical image data that is in a particular format, such as pixels, two-dimensional, one-dimensional or other data obtained from an imaging process of a patient. The image data is accessed by defining
unit 802. The definingunit 802 defines a plurality of computing nodes that are available to perform processing operations, manipulations and/or functions. The defined computing nodes may be defined, or identified by a user, or program code by sending an API (Application Program Interface), or “ping” to possible computing nodes as a status check to determine all possible computing nodes that may be available to perform processing operations. - The
determination unit 804 is used to determine which of the plurality of computing nodes is available for performing processing. Since all possible nodes that are identified by the defining unit may not be available to actually perform proceeding functionality, the determiningunit 804 can select those nodes that respond to the API or ping, as actually receptive to processing requests. - The
parsing unit 806 is used for parsing the medical data into a plurality of medical data subsets. The number of the medical data subsets being based on the number of the available computing nodes, or processing nodes, 807(a) . . . (n). The number of subsets may be a function of the nodes (generally 807) processing power, or capability, or speed. Indeed one embodiment of the present invention is that the number of subsets is equal to the number ofprocessing nodes 807. Alternatively, each of theprocessing nodes 807 may receive a disproportionate amount of subsets based on the processing capability of eachnode 807. Specifically, somenode 807 that are available may not receive any subsets, while other ones of thenodes 807 may receive a plurality of subsets. - The
processing unit 808 is used for processing, organizing, compiling and/or re-assembling each subset received from an associated one of the plurality ofcomputing nodes 807. - Alternatively, the
processing unit 808 may perform actual processing functionality of one or more subsets of data itself. Thisprocessing unit 808 is typically used as a managing, or control processing unit, to control the final processing of the processed data received fromnodes 807. - The transmitting
unit 810 is used to transmit the processed medical data subsets to a master node, which may be processingunit 808, or other node. - The generating
unit 812 is used for generating a representation of the image data at the master node by combining the processed medical data subsets. The representation may be, for example, a three-dimensional (3D) representation, a voxel representation, a color representation or model of the image data. - The
output unit 814 is used to output the representation, Thisunit 814 may be a computer screen, printer or other suitable output device to display or output the representation. Thememory 816 is also available to store the representation output fromoutput module 816. - While a preferred embodiment of the present invention has been described above, it should be understood that it has been presented by way of example only, and not limitation. Thus, the breadth and scope of the present invention should not be limited by the above described exemplary embodiment.
- Obviously, numerous modifications and variations of the present invention are possible in light of the above teachings. It is therefore to be understood that the invention may be practiced otherwise than as specifically described herein.
Claims (16)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/604,954 US8818066B2 (en) | 2004-06-29 | 2012-09-06 | Grid computing on radiology network |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/880,112 US8285826B2 (en) | 2004-06-29 | 2004-06-29 | Grid computing on radiology network |
US13/604,954 US8818066B2 (en) | 2004-06-29 | 2012-09-06 | Grid computing on radiology network |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/880,112 Continuation-In-Part US8285826B2 (en) | 2004-06-29 | 2004-06-29 | Grid computing on radiology network |
Publications (2)
Publication Number | Publication Date |
---|---|
US20130058554A1 true US20130058554A1 (en) | 2013-03-07 |
US8818066B2 US8818066B2 (en) | 2014-08-26 |
Family
ID=47753219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/604,954 Active 2025-02-22 US8818066B2 (en) | 2004-06-29 | 2012-09-06 | Grid computing on radiology network |
Country Status (1)
Country | Link |
---|---|
US (1) | US8818066B2 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104182606A (en) * | 2013-12-24 | 2014-12-03 | 中国科学院苏州生物医学工程技术研究所 | PET/CT distributive software system and medical equipment |
US10061899B2 (en) | 2008-07-09 | 2018-08-28 | Baxter International Inc. | Home therapy machine |
US20220175336A1 (en) * | 2020-12-03 | 2022-06-09 | Konica Minolta, Inc. | Radiographic image capturing device, radiographic image capturing system, control method, and control program |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20200009435A (en) | 2018-07-19 | 2020-01-30 | 삼성전자주식회사 | Method of managing data representation for deep learning, method of processing data for deep learning and deep learning system performing the same |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6269408B1 (en) * | 1996-05-01 | 2001-07-31 | Sun Microsystems, Inc. | Method for creating a single binary virtual device driver for a windowing operating system |
US6587598B1 (en) * | 1999-02-18 | 2003-07-01 | Koninklijke Philips Electronics N.V. | Image processing method, system and apparatus for forming an overview image of an elongated scene |
US7218766B2 (en) * | 2002-04-15 | 2007-05-15 | General Electric Company | Computer aided detection (CAD) for 3D digital mammography |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050060202A1 (en) | 2002-05-31 | 2005-03-17 | Richard Taylor | System and method for coupling a plurality of medical devices in serverless grid |
US7720526B1 (en) | 2003-02-04 | 2010-05-18 | Modell Mark D | Self-interfering tomography system |
US20060241968A1 (en) | 2003-06-04 | 2006-10-26 | Hollebeek Robert J | Ndma scalable archive hardware/software architecture for load balancing, independent processing, and querying of records |
US8064979B2 (en) | 2003-06-09 | 2011-11-22 | General Electric Company | Tempero-spatial physiological signal detection method and apparatus |
US7627617B2 (en) | 2004-02-11 | 2009-12-01 | Storage Technology Corporation | Clustered hierarchical file services |
US8583449B2 (en) | 2004-03-22 | 2013-11-12 | Avaya Inc. | Method and apparatus for providing network based load balancing of medical image data |
US8280483B2 (en) | 2006-06-14 | 2012-10-02 | Koninklijke Philips Electronics N.V. | Multi-modality medical image viewing |
-
2012
- 2012-09-06 US US13/604,954 patent/US8818066B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6269408B1 (en) * | 1996-05-01 | 2001-07-31 | Sun Microsystems, Inc. | Method for creating a single binary virtual device driver for a windowing operating system |
US6587598B1 (en) * | 1999-02-18 | 2003-07-01 | Koninklijke Philips Electronics N.V. | Image processing method, system and apparatus for forming an overview image of an elongated scene |
US7218766B2 (en) * | 2002-04-15 | 2007-05-15 | General Electric Company | Computer aided detection (CAD) for 3D digital mammography |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10061899B2 (en) | 2008-07-09 | 2018-08-28 | Baxter International Inc. | Home therapy machine |
US10068061B2 (en) | 2008-07-09 | 2018-09-04 | Baxter International Inc. | Home therapy entry, modification, and reporting system |
US10095840B2 (en) | 2008-07-09 | 2018-10-09 | Baxter International Inc. | System and method for performing renal therapy at a home or dwelling of a patient |
US10224117B2 (en) | 2008-07-09 | 2019-03-05 | Baxter International Inc. | Home therapy machine allowing patient device program selection |
US10089443B2 (en) | 2012-05-15 | 2018-10-02 | Baxter International Inc. | Home medical device systems and methods for therapy prescription and tracking, servicing and inventory |
CN104182606A (en) * | 2013-12-24 | 2014-12-03 | 中国科学院苏州生物医学工程技术研究所 | PET/CT distributive software system and medical equipment |
US20220175336A1 (en) * | 2020-12-03 | 2022-06-09 | Konica Minolta, Inc. | Radiographic image capturing device, radiographic image capturing system, control method, and control program |
Also Published As
Publication number | Publication date |
---|---|
US8818066B2 (en) | 2014-08-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8041093B2 (en) | System and method for definition of DICOM header values | |
US7634121B2 (en) | Method and system for rule-based comparison study matching to customize a hanging protocol | |
US6904161B1 (en) | Workflow configuration and execution in medical imaging | |
US10673922B2 (en) | Cloud based 2D dental imaging system with HTML web browser acquisition | |
CN100452067C (en) | Medical image data transmission and three-dimension visible sysem and its implementing method | |
CN102576471B (en) | Generate the view of medical image | |
US7961921B2 (en) | System and method for medical diagnosis and tracking using three-dimensional subtraction in a picture archiving communication system | |
US20140369577A1 (en) | Medical imaging reconstruction optimized for recipient | |
US8725801B2 (en) | Systems and methods for image sharing in a healthcare setting while maintaining diagnostic image quality | |
US20030139944A1 (en) | System and method for the processing of patient data | |
Wong et al. | A hospital integrated framework for multimodality image base management | |
US20080292162A1 (en) | Method and System for Generating a Collage to Summarize a Medical Dataset | |
US8818066B2 (en) | Grid computing on radiology network | |
US20240194325A1 (en) | Systems and Methods for Processing Medical Images For In-Progress Studies | |
US20060269106A1 (en) | System and method for optimizing throughput of medical evidence data to and from long term digital storage solutions | |
Wong et al. | A digital library for biomedical imaging on the Internet | |
Wong et al. | Networked multimedia for medical imaging | |
Society for Imaging | Practical imaging informatics: foundations and applications for PACS professionals | |
WO2021105312A1 (en) | Systems and methods for processing medical images using relevancy rules | |
US8285826B2 (en) | Grid computing on radiology network | |
US8156210B2 (en) | Workflow for computer aided detection | |
Stoian et al. | Current trends in medical imaging acquisition and communication | |
Lim et al. | The digital imaging and communications in medicine (DICOM): description, structure and applications | |
US11941022B2 (en) | Systems and methods for database synchronization | |
KR20200120578A (en) | Medical image information starage system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SIEMENS MEDICAL SOLUTIONS USA, INC., PENNSYLVANIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BATTLE, XAVIER;FANG, JOSEPH Y.;SIGNING DATES FROM 20121103 TO 20121107;REEL/FRAME:029294/0926 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551) Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 8 |